Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/szoloth/skill-pack/mcp-buildernpx skills add SZoloth/skill-pack --skill mcp-buildergit clone --depth 1 https://github.com/SZoloth/skill-packWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/szoloth/skill-pack/mcp-builder)<a href="https://agentmods.dev/skills/szoloth/skill-pack/mcp-builder"><img src="https://agentmods.dev/badge/skills/szoloth/skill-pack/mcp-builder.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00061 | $0.02865 |
| Opus 5 | $0.00030 | $0.01432 |
| Sonnet 5 | $0.00012 | $0.00573 |
| Haiku 4.5 | $0.00006 | $0.00286 |
Grade A, and why
mcp-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to mcp-builder — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Development Guide
Overview
To create high-quality MCP (Model Context Protocol) servers that enable LLMs to effectively interact with external services, use this skill. An MCP server provides tools that allow LLMs to access external services and APIs. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks using the tools provided.
Process
🚀 High-Level Workflow
Creating a high-quality MCP server involves four main phases:
Phase 1: Deep Research and Planning
1.1 Understand Agent-Centric Design Principles
Before diving into implementation, understand how to design tools for AI agents by reviewing these principles:
Build for Workflows, Not Just API Endpoints:
- Don't simply wrap existing API endpoints - build thoughtful, high-impact workflow tools
- Consolidate related operations (e.g.,
schedule_eventthat both checks availability and creates event) - Focus on tools that enable complete tasks, not just individual API calls
- Consider what workflows agents actually need to accomplish
Optimize for Limited Context:
- Agents have constrained context windows - make every token count
- Return high-signal information, not exhaustive data dumps
- Provide "concise" vs "detailed" response format options
- Default to human-readable identifiers over technical codes (names over IDs)
- Consider the agent's context budget as a scarce resource
Design Actionable Error Messages:
- Error messages should guide agents toward correct usage patterns
- Suggest specific next steps: "Try using filter='active_only' to reduce results"
- Make errors educational, not just diagnostic
- Help agents learn proper tool usage through clear feedback
Follow Natural Task Subdivisions:
- Tool names should reflect how humans think about tasks
- Group related tools with consistent prefixes for discoverability
- Design tools around natural workflows, not just API structure
Use Evaluation-Driven Development:
- Create realistic evaluation scenarios early
- Let agent feedback drive tool improvements
- Prototype quickly and iterate based on actual agent performance
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- LICENSE.txt 11 KB
- reference/evaluation.md 21 KB
- reference/mcp_best_practices.md 28 KB
- reference/node_mcp_server.md 26 KB
- reference/python_mcp_server.md 26 KB
- scripts/connections.py 4.8 KB runs code
- scripts/evaluation.py 12 KB runs code
- scripts/example_evaluation.xml 1.2 KB
- scripts/requirements.txt 29 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 329 lines · 61 tokens per session scan A b1010e90adcb
mcp-builder is a skill published in the GitHub repository SZoloth/skill-pack (14 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 2,865 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mcp-builder, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
narrative-text-visualization
Generate structured narrative text visualizations from data using T8 Syntax. Use when users want to create data interpretation reports, summaries, or structured articles with semantic entity annotations. T8 is designed for unstructured data visualization where T stands for Text and 8 represents a byte of 8 bits…
gpt-vis
推荐并生成合适的数据可视化图表，使用 GPT-Vis 库。支持两种输出模式：（1）语法模式——生成 Syntax 或 JSON 配置；（2）代码模式——生成完整的运行代码。支持 26 种图表类型。.
antv-x6-editor
Use this skill whenever the user wants to create, customize, or troubleshoot X6 v3 graph editor diagrams. Triggers include: any mention of 'X6', 'antv x6', '@antv/x6', 'X6 editor', 'X6 图编辑', '流程图', 'DAG', 'ER图', '实体关系图', '血缘图', '组织架构图', 'UML类图', 'flowchart', 'DAG diagram', 'ER diagram', 'lineage graph', 'org chart'…
infographic-creator
Create beautiful infographics based on given text content. Use when users request to create infographics.
antv-g2-chart
Use this skill whenever the user wants to create, customize, or troubleshoot G2 v5 chart visualizations. Triggers include: any mention of 'G2', 'antv g2', '@antv/g2', 'G2 chart', 'G2 可视化', or requests to produce charts like bar charts (柱状图), line charts (折线图), pie charts (饼图), scatter plots (散点图), area charts (面积图)…
antv-g6-graph
Use this skill whenever the user wants to create, customize, or troubleshoot G6 v5 graph/network visualizations. Triggers include: any mention of 'G6', 'antv g6', '@antv/g6', 'G6 graph', 'G6 图', '网络图', '关系图', '拓扑图', '树形图', '流程图', '思维导图', '鱼骨图', '力导向图', 'force graph', 'network visualization', 'node-edge diagram'…